A systematic explainability study of Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Vision Mamba (ViM) found that CNNs produce more spatially diffuse saliency maps that correlat…
LayerRoPE, a depth-wise positional encoding method presented in arXiv paper 2610.09179v1, replaces all layerwise normalization weight vectors in a Transformer with a single shared vector and depth-con…
Researchers introduced SGMA, a structure-guided masked autoencoding framework for ultra-high-resolution scientific images, detailed in arXiv paper 2609.30682v1. SGMA combines a content-adaptive quadtr…
Researchers introduced NeuroStrata, a connectivity-aware deep representation learning framework for EEG-based mental stress analysis, achieving a peak accuracy of 97.3% using the LAION-CLIP-ViT-L14 ba…
A dissertation from a researcher at an unnamed institution proposes modular parameter-efficient continual learning for Vision Transformers, organizing adaptation into small role-matched corrections ra…
Researchers have introduced GradSkip, a new method for Vision Transformers that uses adaptive head weighting and re-evaluates residual connections to achieve a 14-times reduction in GFLOPs while impro…
Vision Transformers (ViTs) robustly encode Gestalt-like figure-ground cues such as surroundedness and convexity from natural images, according to a study evaluating 25 ViTs with supervised and self-su…
Researchers introduced HetDPT, a depth pruning method for Vision Transformers that speeds up DeiT-B by 1.58x and DeiT-S by 1.39x with minimal accuracy loss, and combined with width pruning (HetDPT+) a…
Researchers introduced FlexViT, a reconfigurable FPGA accelerator that achieves up to 2.74x speedup for Vision Transformer layers on edge devices. The accelerator uses a hardware-software co-design ap…
Researchers introduce Depth-wise Gradient Augmentation, a new optimization paradigm that transforms layer-wise updates to exploit structured relationships across deep neural network layers. Their inst…
Researchers have developed DiffusionBlocks, a framework that partitions transformer neural networks into independently trainable blocks to reduce memory requirements proportionally while maintaining c…